Update app.py

app.py

@@ -2,9 +2,10 @@ import transformers
 from transformers import AutoTokenizer
 import torch
 from transformers import pipeline
+import gradio as gr
 
 model = "meta-llama/Llama-2-7b-chat-hf"
-tokenizer = AutoTokenizer.from_pretrained(model, use_auth_token=True)
+tokenizer = AutoTokenizer.from_pretrained(model, use_auth_token=False)
 
 SYSTEM_PROMPT = """<s>[INST] <<SYS>>
 You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.
@@ -56,6 +57,5 @@ def llama_response(message: str, history: list) -> str:
     print("Chatbot:", response.strip())
     return response.strip()
 
-import gradio as gr
 
 gr.ChatInterface(llama_response).launch()